Hugging Face's logo

maxkordn
/
Qwen2.5-Coder-7B-Instruct-Solver-RFT

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
cogzero
trl
sft
kordn
conversational
text-generation-inference
Model card Files
xet
Community
maxkordn commited on
Commit
156a661
·
verified ·
1 Parent(s): 783a727

Model save

Browse files
Files changed (3) hide show
  1. all_results.json +6 -11
  2. train_results.json +6 -6
  3. trainer_state.json +0 -0
all_results.json CHANGED
@@ -1,13 +1,8 @@
1
  {
2
- "eval_loss": 0.10813906788825989,
3
- "eval_runtime": 52.8222,
4
- "eval_samples": 2505,
5
- "eval_samples_per_second": 47.423,
6
- "eval_steps_per_second": 5.944,
7
- "total_flos": 7.792360049627628e+17,
8
- "train_loss": 0.04186144905114496,
9
- "train_runtime": 7507.8207,
10
- "train_samples": 14169,
11
- "train_samples_per_second": 9.436,
12
- "train_steps_per_second": 0.074
13
  }
 
1
  {
2
+ "total_flos": 9.471448716243108e+17,
3
+ "train_loss": 0.017112477973285245,
4
+ "train_runtime": 9496.6509,
5
+ "train_samples": 15697,
6
+ "train_samples_per_second": 8.264,
7
+ "train_steps_per_second": 0.065
 
 
 
 
 
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "total_flos": 7.792360049627628e+17,
3
- "train_loss": 0.04186144905114496,
4
- "train_runtime": 7507.8207,
5
- "train_samples": 14169,
6
- "train_samples_per_second": 9.436,
7
- "train_steps_per_second": 0.074
8
  }
 
1
  {
2
+ "total_flos": 9.471448716243108e+17,
3
+ "train_loss": 0.017112477973285245,
4
+ "train_runtime": 9496.6509,
5
+ "train_samples": 15697,
6
+ "train_samples_per_second": 8.264,
7
+ "train_steps_per_second": 0.065
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff